检索结果-内蒙古大学图书馆

Exploiting the Intrinsic Neighborhood Semantic Structure for Domain Adaptation in EEG-based Emotion Recognition

IEEE Transactions on Affective Computing 2025年

作者： Yang, Yi Wang, Ze Song, Yu Jia, Ziyu Wang, Boyu Jung, Tzyy-Ping Wan, Feng Macau University of Science and Technology Macao Centre for Mathematical Sciences Respiratory Disease AI Laboratory on Epidemic Intelligence and Medical Big Data Instrument Applications Faculty of Innovation Engineering 999078 China Tianjin University of Technology School of Electrical Engineering and Automation Tianjin Key Laboratory of New Energy Power Conversion Transmission and Intelligent Control Tianjin300384 China Chinese Academy of Sciences Beijing Key Laboratory of Brainnetome and Brain-Computer Interface and Brainnetome Center Institute of Automation Beijing100045 China Western University Department of Computer Science Brain Mind Institute LondonONN6A 3K7 Canada University of California at San Diego Swartz Center for Computational Neuroscience Institute for Neural Computation La Jolla CA92093 United States University of Macau Department of Electrical and Computer Engineering Faculty of Science and Technology China University of Macau Centre for Cognitive and Brain Sciences Centre for Artificial Intelligence and Robotics Institute of Collaborative Innovation 999078 China

Due to the inherent non-stationarity and individual differences present in electroencephalogram (EEG) signals, developing a generalizable model that performs well on new subjects is challenging in EEG-based emotion recognition. Most existing domain adaptation (DA) methods typically mitigate these discrepancies by aligning the marginal distributions of domain feature representations. However, when there is a significant difference in the class-conditional distribution between domain features and labels, the domain-invariant features learned by aligning marginal distributions may have limited discriminative ability for unlabeled target instances or even prove counterproductive. To address this issue, we propose a Neighborhood Semantic Aware Learning-based Dynamic Graph Attention Convolution (NSAL-DGAT) approach that learns target semantic information by considering the inter-domain semantic topological structure, thereby improving classifier adaptation for target instances. Specifically, the proposed NSAL framework is designed to capitalize on the insight that after domain feature alignment, some target samples and their neighboring source samples exhibit similar semantics. By leveraging the neighborhood topological structure, we extract and incorporate semantic target features to train a more transferable classifier. Besides, we implement an entropy weighting mechanism to emphasize representative target semantic information, encouraging target instances to prioritize high-confidence individuals within the source neighborhood. We have conducted extensive experiments on the public SEED dataset and our collected the Hearing-Impaired EEG Dataset (HIED). The experimental results underscore the efficacy of our proposed NSAL-DGAT approach, showcasing state-of-the-art accuracy in subject-dependent as well as subject-independent scenarios. The source code is available at https://***/YYingDL/NSAL-DGAT. © 2010-2012 IEEE.

关键词： Speech analysis

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Methodology of Field-Oriented control Design With Parameter Variation Analysis for Interior Permanent Magnet Synchronous Machine Drives

引用

IEEE Access 2025年 13卷 89524-89541页

作者： Tiago Davi Curi Busarello Abdullah Bubshait Oruganti V. S. R. Varaprasad Abdulhakeem Alsaleem Marcelo Godoy Simões Department of Control Automation and Computation Engineering Federal University of Santa Catarina Florianopolis Brazil Department of Electrical Engineering College of Engineering King Faisal University Al Ahsa Saudi Arabia Smart Transportation Electrification and Energy Research (STEER) Group Department of Electrical Computer and Software Engineering Faculty of Engineering and Applied Science Ontario Tech University Oshawa ON Canada Department of Electrical Engineering College of Engineering Qassim University Buraydah Saudi Arabia School of Technology and Innovations University of Vaasa Vaasa Finland

This paper proposes a comprehensive methodology for Field-Oriented control (FOC) with parameter variation analysis for Interior Permanent Magnet Synchronous Machines (IPMSM). The modeling approach for an IPMSM is first presented, followed by a step-by-step procedure for designing a vector-controlled strategy. The formulation is based on a dq-rotating reference frame aligned with the rotor shaft position. A key distinction of this methodology from traditional approaches is that the current controller is designed in the time domain based on desired time constants, while the speed control is formulated within a frequency response domain framework. The proposed hybrid approach enables accurate tuning of the Proportional-Integrator (PI) controllers for both current and speed control loops. Additionally, a parameter variation analysis is conducted to enhance the proposed methodology. The validity region for the design procedure is presented, ensuring that for any wide speed variation of the machine, loop gains are properly tuned. One of the main advantages of the proposed methodology is that it provides a fast, reliable, and accurate technique for implementing IPMSM drive systems. Results from a controller Hardware-in-the-Loop (C-HIL) setup with an external microcontroller are presented. The comprehensive design approach is validated under two different IPMSM parameter sets, demonstrating its effectiveness.

关键词： PI control Stators Tuning Mathematical models Velocity control Rotors Vectors Stator windings Robustness Microcontrollers

来源：评论

学校读者我要写书评

暂无评论

Ground vehicle detection through aerial images taken by a UAV 17

Ground vehicle detection through aerial images taken by a UA...

引用

17th International Conference on Information Fusion, FUSION 2014

作者： Pérez, Alberto Chamoso, Pablo Parra, Víctor Sánchez, Antonio Juan Computer and Automation Control Department Faculty of Science University of Salamanca Salamanca Spain

ISBN: (纸本)9788490123553

Advantages in the application of intelligent approaches, such as the conjunction of artificial vision and Unmanned Aerial Vehicles (UAV), have been recently emerging. This paper presents a system capable of detecting ground vehicles through aerial images taken by a UAV in real time. In addition, the system offers the possibility to autonomously guide the UAV to keep track of a vehicle that has been previously detected. © 2014 International Society of Information Fusion.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Distributed Constrained Online Nonconvex Optimization with Compressed Communication

arXiv

引用

arXiv 2025年

作者： Zhang, Kunpeng Xu, Lei Yi, Xinlei Cao, Ming Johansson, Karl H. Chai, Tianyou Yang, Tao State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China Department of Mechanical Engineering University of Victoria VictoriaBCV8W 2Y2 Canada Shanghai Institute of Intelligent Science and Technology National Key Laboratory of Autonomous Intelligent Unmanned Systems Frontiers Science Center for Intelligent Autonomous Systems Ministry of Education Shanghai201210 China Engineering and Technology Institute Groningen Faculty of Science and Engineering University of Groningen GroningenAG 9747 Netherlands Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Sweden Digital Futures Stockholm10044 Sweden

This paper considers distributed online nonconvex optimization with time-varying inequality constraints over a network of agents. For a time-varying graph, we propose a distributed online primal–dual algorithm with compressed communication to efficiently utilize communication resources. We show that the proposed algorithm establishes an O(T max{1−θ1,θ1}) network regret bound and an O(T 1−θ1/2) network cumulative constraint violation bound, where T is the number of iterations and θ1 ∈ (0, 1) is a user-defined trade-off parameter. When Slater’s condition holds (i.e, there is a point that strictly satisfies the inequality constraints at all iterations), the network cumulative constraint violation bound is reduced to O(T 1−θ1). These bounds are comparable to the state-of-the-art results established by existing distributed online algorithms with perfect communication for distributed online convex optimization with (time-varying) inequality constraints. Finally, a simulation example is presented to validate the theoretical results. Copyright © 2025, The Authors. All rights reserved.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Fast convergent on-board Li-ion battery state of charge estimation via back-forth moving horizon estimation

引用

IEEE Transactions on Power Electronics 2025年

作者： Liu, Zhihao Xiao, Yu Yuan, Yuan Xu, Xiaodong Luo, Biao Huang, Tingwen Ministry of Education School of Automation and Key Laboratory of Industrial Intelligence and Systems Central South University Changsha 410083 China Shenzhen University of Advanced Technology Faculty of Computer Science and Control Engineering Shenzhen China

Accurate state of charge (SOC) estimation is crucial for the safe operation of lithium-ion batteries (LIBs), yet existing methods are limited by sensitivity to initial SOC guess or high computational complexity. To address these challenges, this study proposes an onboard back-forth moving horizon estimation (BFMHE) framework for SOC estimation, achieving high precision, robustness, and computational efficiency compatible with microcontroller implementation. An efficient linear equivalent circuit model (ECM) is established, where the open-circuit voltage-SOC relationship is approximated by piecewise linear functions. The proposed framework employs two MHE estimators that iteratively operate in opposite directions over a finite time horizon, which enables rapid convergence. Moreover, this study provides a rigorous proof of the stability of the BFMHE method for the battery system with current input. The proposed approach is validated experimentally under various operating conditions and with different initial SOC guesses. Experimental results show that the proposed onboard BFMHE method achieves a maximum estimation error of less than 1% and quickly converges to the true SOC value, demonstrating strong robustness to initial estimation errors. © 1986-2012 IEEE.

关键词： Back-forth moving horizon estimation Convergence analysis Lithium-ion battery State of charge estimation

来源：评论

学校读者我要写书评

暂无评论

Agent DEVS simulation of the evacuation process from a commercial building during a fire 12th

Agent DEVS simulation of the evacuation process from a comme...

引用

12th International Scientific and Technical Conference computer science and Information Technologies, CSIT 2017

作者： Kulakowski, Andrzej Rogala, Bartosz Faculty of Electrical Engineering Automation Control and Computer Science Kielce University of Technology Kielce Poland

ISBN: (纸本)9783319705804

The paper describes a simulation application for the process of evacuating people from a building in the event of a fire. This simulation was developed as an agent system using the DEVS formalism. The following sections show the design and implementation of such a system using the Adevs library. A series of simulation tests were then performed for different simulation scenarios. © 2018, Springer International Publishing AG.

关键词： Office buildings

来源：评论

学校读者我要写书评

暂无评论

Composition of united multiple diseases evolution topological model

Composition of united multiple diseases evolution topologica...

引用

9th International Symposium on Intelligent Systems and Informatics, SISY 2011

作者： Karpičs, I. Markovičs, Z. Markoviča, I. Institute of Computer Control Automation and Computer Engineering Faculty of Computer Science and Information Technology Riga Technical University Riga Latvia

ISBN: (纸本)9781457719745

Mathematical models are constructed and used as a methodology of various functioning systems structure investigation and performance analysis. The main goal of mathematical model usage is to perform wholesome diagnostics and correct work resumption of investigated system. In the article topological modeling method has been investigated by giving fundamental basics and application spheres by examples. Authors propose model construction method with an example from medicine by creating multiple diseases (arterial hypertension, atherosclerosis and diabetes mellitus) evolution topological model with formal aspects. Developed modeling method and united diseases model can be used to prognosticate evolution of diseases, perform inspection of used therapies and provide information for optimal therapy complex selection. © 2011 IEEE.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Personalized therapy selection by using multi-objective optimization

Personalized therapy selection by using multi-objective opti...

引用

IEEE 16th International Conference on Intelligent Engineering Systems, INES 2012

作者： Karpics, Ivars Institute of Computer Control Automation and Computer Engineering Faculty of Computer Science and Information Technology Riga Technical University Riga Latvia

ISBN: (纸本)9781467326957

In the article a therapy selection method by using topological modelling and multi- objective optimization is presented. In a medicine practice a doctor by taking into the count patients' health state and laboratory results, tries to suggest a treatment strategy, which mostly is a drug therapy. To solve this task a decision support system has been developed and proposed. The system includes a mathematical model of three self connected diseases. Therapies are evaluated by five efficiency objectives. To find the optimal therapy, seven multi- objective methods are selected and used. Optimization methods form decision support module which is implemented in the medical computer system. To evaluate a performance of the system, test examples are analysed. Conclusion includes the summary and proposals of further research. © 2012 IEEE.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Prox-DBRO-VR: A Unified Analysis on Byzantine-Resilient Decentralized Stochastic Composite Optimization With Variance Reduction and Nonasymptotic Convergence Rates

引用

IEEE Transactions on Systems, Man, and Cybernetics: Systems 2025年

作者： Hu, Jinhui Chen, Guo Li, Huaqing Guo, Xiaoyu Ran, Liang Huang, Tingwen Central South University School of Automation Hunan Changsha 410083 China City University of Hong Kong Department of Mechanical Engineering Hong Kong University of New South Wales School of Electrical Engineering and Telecommunications Sydney 2052 NSW Australia Southwest University Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing College of Electronic and Information Engineering Chongqing 400715 China Shenzhen University of Advanced Technology Faculty of Computer Science and Control Engineering Shenzhen 518055 China

Decentralized stochastic gradient algorithms efficiently solve large-scale finite-sum optimization problems when all agents in the network are reliable. However, most of these algorithms are not resilient to adverse conditions, such as malfunctioning agents, software bugs, and cyber attacks. This article aims to handle a class of general composite optimization problems over multiagent systems (MASs) in the presence of an unknown number of Byzantine agents. Building on a resilient aggregation mechanism and the proximal-gradient mapping method, a Byzantine-resilient decentralized stochastic proximal-gradient algorithmic framework is proposed, dubbed Prox-DBRO-VR, which achieves an optimization and control goal using only local computations and communications. To asymptotically reduce the noise variance arising from local gradient estimation and accelerate the convergence, we incorporate two localized variance-reduced (VR) techniques (SAGA and LSVRG) into Prox-DBRO-VR to design Prox-DBRO-SAGA and Prox-DBRO-LSVRG. By analyzing the contraction relationships among the gradient-learning error, resilient consensus condition, and convergence error in a unified theoretical framework, it is proved that both Prox-DBRO-SAGA and Prox-DBRO-LSVRG, with a well-designed constant (resp., decaying) step-size, converge linearly (resp., sublinearly) inside an error ball around the optimal solution to the original problem under standard assumptions. A tradeoff between convergence accuracy and Byzantine resilience in both linear and sublinear cases is also characterized. In numerical experiments, the effectiveness and practicability of the proposed algorithms are manifested via resolving a decentralized sparse machine learning problem under various Byzantine attacks. © 2013 IEEE.

关键词： Byzantine-resilient algorithms composite optimization decentralized stochastic optimization system security variance reduction

来源：评论

学校读者我要写书评

暂无评论

Formation control with obstacle avoidance of second-order multi-agent systems under directed communication topology

引用

science China(Information sciences) 2019年第9期62卷 144-157页

作者： Guoxing WEN C.L.Philip CHEN Hui DOU Hongli YANG Chunfang LIU College of Science Binzhou University Department of Computer and Information Science Faculty of Science and Technology University of Macau College of Navigation Dalian Maritime University State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of Sciences Mathematics and Systems Science College Shandong University of Science and Technology

This paper addresses the obstacle avoidance problem of formation control for the multi-agent systems modeled by double integrator dynamics under a directed interconnection topology. The control task is finished by a leader-follower formation scheme combined with an artificial potential field(APF) *** leader-follower scheme is carried out by taking the desired trajectory with the desired velocity as virtual leader, while the APF method is carried out by dealing with the obstacles as the high potential points. When the obstacle avoidance tasks are finished, the artificial potential forces degrade the formation performance, so their undesired effects are treated as disturbances, which is analyzed by the robust H∞performance. Based on Lyapunov stability theory, it is proved that the proposed formation approach can realize the control objective. The result is also extended to the switching multi-agent formation. The effectiveness of the proposed formation scheme is further confirmed by simulation studies.

关键词： formation control obstacle avoidance artificial potential field method H_∞ performance second-order multi-agent system directed topology

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：